fix: honor train_bn in BackboneFinetuning.freeze_before_training#21652
Open
javierdejesusda wants to merge 1 commit into
Open
fix: honor train_bn in BackboneFinetuning.freeze_before_training#21652javierdejesusda wants to merge 1 commit into
javierdejesusda wants to merge 1 commit into
Conversation
javierdejesusda
requested review from
ethanwharris,
justusschock and
tchaton
as code owners
Codecov Report✅ All modified and coverable lines are covered by tests.
Additional details and impacted files@@ Coverage Diff @@
## master #21652 +/- ##
=========================================
- Coverage 87% 79% -8%
=========================================
Files 270 267 -3
Lines 23934 23875 -59
=========================================
- Hits 20713 18798 -1915
- Misses 3221 5077 +1856 |
…ning freeze_before_training() called self.freeze(pl_module.backbone) without forwarding self.train_bn, so BatchNorm layers stayed trainable during the initial frozen phase regardless of the train_bn setting. The unfreezing path already passed the flag correctly.
javierdejesusda
force-pushed
the
bugfix/21531_backbone-finetuning-train-bn
branch
from
55c2ea2 to
92a2a3c
Compare
|
Codecov Report✅ All modified and coverable lines are covered by tests.
Additional details and impacted files@@ Coverage Diff @@
## master #21652 +/- ##
=========================================
- Coverage 87% 79% -8%
=========================================
Files 270 267 -3
Lines 23973 23914 -59
=========================================
- Hits 20751 18801 -1950
- Misses 3222 5113 +1891 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes #21531
BackboneFinetuning.freeze_before_training()calledself.freeze(pl_module.backbone)without forwarding thetrain_bnparameter, so BatchNorm layers stayed trainable during the initial frozen phase regardless of thetrain_bnsetting passed to the constructor.The unfreezing path in
finetune_function()already passedtrain_bn=self.train_bncorrectly — this change makes the freezing path consistent.Before submitting
BackboneFinetuning:train_bnonly applied during unfreezing phase #21531)📚 Documentation preview 📚: https://pytorch-lightning--21652.org.readthedocs.build/en/21652/